Jana BergantandClaude Opus 4.6 f7d2cce86b fix: correct Qwen3.5 model sizes and MLX repos in catalog ...

The model catalog listed non-existent Qwen3.5 sizes (3B, 8B, 14B) and
pointed to MLX community repos that don't exist, causing `jarvis init`
to recommend models that cannot be downloaded on Apple Silicon.

Replace with the actual Qwen3.5 model family sizes (0.8B, 2B, 9B, 27B)
and verified mlx-community repo URLs from HuggingFace.

Fixes #129

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-03-26 08:29:31 +01:00

..

__init__.py

init commit

2026-03-12 17:29:39 +00:00

test_intelligence_stubs.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_model_catalog_extended.py

fix: correct Qwen3.5 model sizes and MLX repos in catalog

2026-03-26 08:29:31 +01:00

test_model_catalog.py

init commit

2026-03-12 17:29:39 +00:00

test_router.py

fix(channels): wire channel→agent handler and fix Telegram send pipeline (#94)

2026-03-20 18:35:18 -07:00

test_routing_models.py

init commit

2026-03-12 17:29:39 +00:00